-
### 🐛 Describe the bug
```python
import torch
from torch import nn, Tensor
from torch.export import export_for_inference, Dim
from torch.nn.attention.flex_attention import flex_attention
class…
-
### Initial Checks
- [X] I have searched Google & GitHub for similar requests and couldn't find anything
- [X] I have read and followed [the docs](https://pydantic-docs.helpmanual.io) and still think…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
```
...
from cuml.linear_model import LogisticRegression
from cuml.metrics import accuracy_score
...
print("Initializing Logistic Regression model...")
model = LogisticRegression()
print("Tra…
-
I tried to run the Virtual Camera example and use the `--onnx_export_path` argument. But it fails with `KeyError: 'camera_2d'`. `camera_2d` is the name of the obs property here. In other examples wher…
-
## 🐛 Bug
Since [version 1.6](https://github.com/pytorch/pytorch/releases/tag/v1.6.0) models are exported with the same serialisation format that is used by TorchScript:
> the same as the TorchScri…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### Ultralytics YOLO Component
Expo…
-
Repro:
// See https://huggingface.co/nvidia/NV-Embed-v1 for installation instructions
// Basically `pip install transformers` and make sure you have huggingface access
```
import torch
import…
-
### 🐛 Describe the bug
Hi team, just reporting this problem. I can bypass it if I replace int with `math.trunc`.
repro:
```
class M(torch.nn.Module):
def forward(self, x):
ori_size…
-
### 🚀 The feature, motivation and pitch
Is there any plan for the `torch.export` team to support the set-based dynamism in addition to range-based dynamism?
Below is a small repro code for discret…